Execute a JavaScript expression or function in the browser page context and return the result. Use when the user wants to run custom JavaScript on the page, read or modify DOM elements, extract data, or perform calculations. Supports async/await — use
AI agents invoke pilot_evaluate to trigger actions in Pilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary JavaScript code within the browser context, which is a classic Execute capability. While read-only JavaScript (e.g., DOM queries) would be lower risk, the tool explicitly supports function execution and async operations, and the description does not limit it to read-only queries.
From the tool's definition Execute a JavaScript expression or function in the browser page context and return the result. Supports async/await.
Documented attack patterns abuse exactly the kind of access pilot_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for pilot_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"pilot_evaluate": {
"limits": [
{
"counter": "pilot_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}pilot_evaluate stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute a JavaScript expression or function in the browser page context and return the result. Use when the user wants to run custom JavaScript on the page, read or modify DOM elements, extract data, or perform calculations. Supports async/await — use. It is categorised as a Execute tool in the Pilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pilot MCP server in PolicyLayer and add a rule for pilot_evaluate: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pilot. Nothing to install.
pilot_evaluate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pilot_evaluate rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for pilot_evaluate. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
pilot_evaluate is provided by the Pilot MCP server (tacosyhorchata/pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 61 Pilot tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
61 Pilot tools catalogued and risk-classified — across an index of 42,500+ MCP servers.